-
Notifications
You must be signed in to change notification settings - Fork 168
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[MiniGPT4] Add MiniGPT4 to SHARK #1554
Conversation
Lets call this "MultiModal" in the UI since I assume we will want to switch out LLMs etc in the future. |
4bdd01a
to
0d7f62a
Compare
a7de215
to
14a2d31
Compare
Hi @powderluv - we can merge this and handle bugs in subsequent PR.
In the subsequent PR - I'd try to handle your comment + automate certain aspect of running this script which currently requires manual intervention + try to get rid of other part of this still huge a code base. Also, I'll have to try for int8 - let me know your thoughts here as well! |
f9ce1ca
to
1495997
Compare
ef2c983
to
5ac977d
Compare
Please lint and we can merge it in and iterate. |
5ac977d
to
aaefacf
Compare
Hi @powderluv |
Is this ready to merge ? |
-- This is the first installment of MiniGPT4 in SHARK. Signed-off-by: Abhishek Varma <[email protected]>
-- This commit adds int8 support for MiniGPT4. Signed-off-by: Abhishek Varma <[email protected]>
aaefacf
to
681a7ea
Compare
ebc974c
to
5336f99
Compare
5336f99
to
a2f27b5
Compare
Hi @powderluv . The CI failure looks unrelated. |
-- This is the first installment of MiniGPT4 in SHARK.
Signed-off-by: Abhishek Varma [email protected]
Download the vmfbs from SHARK Tank
The script currently has changed the vmfb names so it needs to be modified like the latest fp16 Vision Model's vmfb : minigpt4_vision_model_fp16_cuda.vmfb after downloading accordingly (I'm working on refactoring this all and get rid of the manual downloading - this is WIP patch).
Discalimer: This is a pretty big WIP patch